41b951c929
clang emit wrong code sequence for `int16`(`short`) to `__fp16` conversion,
and that should fix the code gen directly is the right way I think,
but I found there is a FIXME comment in clang/Basic/TargetInfo.h say
that's should be removed in future so I think just let swich to using
generic LLVM IR rather than llvm.convert.to.fp16 intrinsics code gen
path is enough.
```
/// Check whether llvm intrinsics such as llvm.convert.to.fp16 should be used
/// to convert to and from __fp16.
/// FIXME: This function should be removed once all targets stop using the
/// conversion intrinsics.
virtual bool useFP16ConversionIntrinsics() const {
return true;
}
```
Reviewed By: craig.topper
Differential Revision: https://reviews.llvm.org/D124509
29 lines
865 B
C
29 lines
865 B
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// RUN: %clang_cc1 -triple riscv64 -emit-llvm %s -o - \
|
|
// RUN: | FileCheck %s
|
|
|
|
__fp16 y;
|
|
short z;
|
|
// CHECK-LABEL: @bar1(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load half, ptr @y, align 2
|
|
// CHECK-NEXT: [[CONV:%.*]] = fpext half [[TMP0]] to float
|
|
// CHECK-NEXT: [[CONV1:%.*]] = fptosi float [[CONV]] to i16
|
|
// CHECK-NEXT: store i16 [[CONV1]], ptr @z, align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void bar1(){
|
|
z = y;
|
|
}
|
|
// CHECK-LABEL: @bar2(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr @z, align 2
|
|
// CHECK-NEXT: [[CONV:%.*]] = sitofp i16 [[TMP0]] to float
|
|
// CHECK-NEXT: [[CONV1:%.*]] = fptrunc float [[CONV]] to half
|
|
// CHECK-NEXT: store half [[CONV1]], ptr @y, align 2
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void bar2(){
|
|
y = z;
|
|
}
|